An efficient algorithm for large-scale detection of protein families Export

@article{enright_02_detection, abstract = {Detection of protein families in large databases is one of the principal research objectives in structural and functional genomics. Protein family classification can significantly contribute to the delineation of functional diversity of homologous proteins, the prediction of function based on domain architecture or the presence of sequence motifs as well as comparative genomics, providing valuable evolutionary insights. We present a novel approach called TRIBE-MCL for rapid and accurate clustering of protein sequences into families. The method relies on the Markov cluster (MCL) algorithm for the assignment of proteins into families based on precomputed sequence similarity information. This novel approach does not suffer from the problems that normally hinder other protein sequence clustering algorithms, such as the presence of multi-domain proteins, promiscuous domains and fragmented proteins. The method has been rigorously tested and validated on a number of very large databases, including SwissProt, InterPro, SCOP and the draft human genome. Our results indicate that the method is ideally suited to the rapid and accurate detection of protein families on a large scale. The method has been used to detect and categorise protein families within the draft human genome and the resulting families have been used to annotate a large proportion of human proteins. 10.1093/nar/30.7.1575}, address = {Computational Genomics Group, The European Bioinformatics Institute, EMBL Cambridge Outstation, Cambridge CB10 1SD, UK. anton@ebi.ac.uk}, author = {Enright, A. J. and Van Dongen, S. and Ouzounis, C. A.}, citeulike-article-id = {159967}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/nar/30.7.1575}, citeulike-linkout-1 = {http://nar.oxfordjournals.org/content/30/7/1575.abstract}, citeulike-linkout-2 = {http://nar.oxfordjournals.org/content/30/7/1575.full.pdf}, citeulike-linkout-3 = {http://nar.oxfordjournals.org/cgi/content/abstract/30/7/1575}, citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/11917018}, citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=11917018}, citeulike-linkout-6 = {http://dx.doi.org/http://dx.doi.org/10.1093/nar/30.7.1575}, citeulike-linkout-7 = {http://dx.doi.org/10.1093/nar/30.7.1575}, comment = {Markov Clustering (MCL) ref.}, day = {1}, doi = {10.1093/nar/30.7.1575}, issn = {1362-4962}, journal = {Nucl. Acids Res.}, keywords = {algorithm, clustering, download, networks, proj\_assembly, toolkit}, month = {April}, number = {7}, pages = {1575--1584}, posted-at = {2008-10-08 12:48:58}, priority = {2}, title = {An efficient algorithm for large-scale detection of protein families}, url = {http://dx.doi.org/10.1093/nar/30.7.1575}, volume = {30}, year = {2002} }

TY - JOUR ID - enright_02_detection L3 - citeulike-article-id:159967 N2 - Detection of protein families in large databases is one of the principal research objectives in structural and functional genomics. Protein family classification can significantly contribute to the delineation of functional diversity of homologous proteins, the prediction of function based on domain architecture or the presence of sequence motifs as well as comparative genomics, providing valuable evolutionary insights. We present a novel approach called TRIBE-MCL for rapid and accurate clustering of protein sequences into families. The method relies on the Markov cluster (MCL) algorithm for the assignment of proteins into families based on precomputed sequence similarity information. This novel approach does not suffer from the problems that normally hinder other protein sequence clustering algorithms, such as the presence of multi-domain proteins, promiscuous domains and fragmented proteins. The method has been rigorously tested and validated on a number of very large databases, including SwissProt, InterPro, SCOP and the draft human genome. Our results indicate that the method is ideally suited to the rapid and accurate detection of protein families on a large scale. The method has been used to detect and categorise protein families within the draft human genome and the resulting families have been used to annotate a large proportion of human proteins. 10.1093/nar/30.7.1575 IS - 7 JF - Nucl. Acids Res. SN - 1362-4962 AD - Computational Genomics Group, The European Bioinformatics Institute, EMBL Cambridge Outstation, Cambridge CB10 1SD, UK. anton@ebi.ac.uk EP - 1584 TI - An efficient algorithm for large-scale detection of protein families VL - 30 SP - 1575 KW - algorithm KW - clustering KW - download KW - networks KW - proj_assembly KW - toolkit N1 - Markov Clustering (MCL) ref. AU - Enright, AJ AU - Van Dongen, S AU - Ouzounis, CA PY - 2002/April/01/ UR - http://dx.doi.org/10.1093/nar/30.7.1575 ER -